File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/abstr/75/t75-2022_abstr.xml
Size: 21,939 bytes
Last Modified: 2025-10-06 13:45:44
<?xml version="1.0" standalone="yes"?> <Paper uid="T75-2022"> <Title>Wilks, Y. &quot;An Artificial Intelligence Approach to Machine Translation.&quot; Computer Models of Thought and</Title> <Section position="2" start_page="0" end_page="0" type="abstr"> <SectionTitle> MOVE RIGHT </SectionTitle> <Paragraph position="0"> =,,uu,u transform in the same way a,J does its wall. If a &quot;center-rectangle&quot; is drawn on a left wall it will appear to project out because one makes the default assumption that any such quadrilateral is actually a rectangle hence must lie in a plane that would so project. In figure 7A, both quadrilaterals could &quot;look like&quot; rectangh.s, but the one to the right does not match the markers for a &quot;left rectangle&quot; subframe (these require, e.g.,, that the left side be longer than the right side). That rectangle is therefore represented by a center-rectangle frame, and seems to project out as though parallel to the center wall.</Paragraph> <Paragraph position="1"> Thus we must not simply assign the .label &quot;rectangle&quot; to a quadrilateral but to a particular frame of a rectangle-system. When we move, we expect&quot;w--hatever space-transformation is applied to the top-level system will be applied also to its subsystems as suggested in figure 7B.</Paragraph> <Paragraph position="2"> Similarly the sequence of elliptical projections of a circle contains congruent pairs that are visually ambiguous as shown in figure 8. But because wall objects usually lie flat, we assume that an ellipse on a left wall is a left-ellipse, expect it to .transform the same way as the left wall, and are * not surprised if the prediction is confirmed.</Paragraph> <Paragraph position="3"> FIC~URE&quot; Io</Paragraph> <Paragraph position="5"> While both Seeing and Imagining result in assignments to frame terminals, Imagination leaves us *wider choices of detail and variety of such assignments. Frames are probably never stored in long-term memory with unassigned \[erminal values. Instead, what really happens is that frames are stored with weakly-bound default assignments at every terminalt These manifest themselves as often-useful but sometimes counter-productive stereotypes.</Paragraph> <Paragraph position="6"> Thus in the sentence &quot;John kicked the ball,&quot; you probably cannot think of a purely abstract ball, but must imagine characteristics of a vaguely particular ball; it probably has a certain default size, default color, default weight. Perhaps it is a descendant of one you first owned or were injured by. Perhaps it resembles your latest one. In any case your image lacks the sharpness of presence because the processes that inspect and operate upon the weakly-bound default features are very likely to change, adapt, or detach them. * WOBI)B, BE~'ITE~CE~ ~l:ll) II~ERI:IIRfi~ The concepts of frame and default assignment seem helpful in discussing the phenomenology of &quot;meaning.&quot; Chomsky (1957) points out that such a sentence as I (A) &quot;colorless green ideas sleep furiously&quot; is treated very differently than the non-sentence (B) &quot;furiously sleep ideas green colorless&quot; and suggests that because both are &quot;equally nonsensical,&quot; what is involved in the recognition of sentences must be quite different from what is involved in the appreciation ef meanings.</Paragraph> <Paragraph position="7"> There is no doubt that there are processes especially concerned with grammar. Since the meaning of an utterance is &quot;encoded&quot; as much in the positional and structural relations between the words as in the word choices themselves, there must be processes concerned with analysing those relations in the course of building the structures that will more directly represent the meaning. What makes the words of (A) more effective and predictable than (B)in producing such a structure -- putting aside the question of whether that structure should be called semantic or syntactic -- is that the word-order relations in (A) exploit the (grammatical) convention and rules people usually use to induce others to make assignments to terminals of structures. This is entirely consistent with grammar theories. A generative grammar.would be a summary description of the exterior appearance of those frame rules -- or their associated processes -- while the operators of transformational grammars seem similar enough to some of our frame transformations.</Paragraph> <Paragraph position="8"> We certainly cannot assume that &quot;logical&quot; meaninglessness has a precise psychological counterpart.</Paragraph> <Paragraph position="9"> Sentence (A) can certainly generate an image! The dominant frame is perhaps .that of someone sleeping; the default system assigns a particular bed, and in it lies a mummy-like shape-frame with a translucent green color property. In this frame there is a terminal for the character of the sleep -restless, perhaps -- and &quot;furiously&quot; seems somewhat inappropriate at that terminal, perhaps because the terminal does not like to accept anything so &quot;intentional&quot; for a sleeper. &quot;Idea&quot; is even more disturbing , because one expects e person, or at least something animate. One senses frustrated procedures trying to resolve these tensions and conflicts more properly, here or there, into the sleeping framework that has been evoked:</Paragraph> <Paragraph position="11"> Utterance (B) does not get nearly so far because no subframeaccepts any substantial fragment. As a result no larger frame finds anything to match its terminals, hence finally, no top level &quot;meaning&quot; or &quot;sentence&quot; frame can organize the utterance as either meaningful or grammatical.</Paragraph> <Paragraph position="12"> By combining this &quot;soft&quot; theory with gradations of assignment tolerances, one could develop systems that degrade properly for sentences with &quot;poor&quot; grammar rather than none~ if the smaller fragments -- phrases and sub-clauses,-- satisfy subframes well enough, an image adequate for certain kinds of comprehension could be constructed anyway, even though some parts of the top level structure are not entirely satisfied, Thus, we arrive at a qualitative theory of &quot;grammatical:&quot; if the top levels are satisfied but some lower terminals are not we have a meaningless sentence; if the top is weak but the bottom solid, we can have an ungrammatical but meaningful utterance.</Paragraph> <Paragraph position="13"> I)t~COBI~E Linguistic activity involves larger structures than can be described in terms of sentential ip'ammar, and these larger structures further blur the distinctness of the wntexsemantic dichotomy. Consider the following fable, as told by W. Chafe ( ! 972): There was once a Wolf who saw a Lamb drinking at a river and wanted an excuse to eat it. For that purpose, even though he himself was upstream, he accused the Lamb of stirring up the water and keeping him from drinklnC/..</Paragraph> <Paragraph position="14"> To understand this, one must realize that the Wolf is lyingt To understand the key conjunctive &quot;even though&quot; one must realize that contamination never flows upstream. This in turn requires us to understand (among other things) the word &quot;upstream&quot; itself. Within a declarative, predicate-based &quot;logical&quot; system, one might try to formalize &quot;upstream&quot; by Butan adequate definition would need a good deal more.</Paragraph> <Paragraph position="15"> What about the fact that the order of things being transported by water currents is not ordinarily changed?. A logician might try to deduce this from a suitably intricate set of '&quot;local&quot; axioms, together with appropriate &quot;induction&quot; axioms. I propose instead to represent this knowledge in a structure that automatically translocates Spatial descriptions from the terminals of one frame to those of another frame of the same system. While this might be considered to be a form of logic, it uses some of the same mechanisms designed for spatial thinking.</Paragraph> <Paragraph position="16"> In many instances we would handle a change over time, or a cause-effect relation, in the same way as we deal with a change in position. Thus, the concept r!ver-flow could evoke a frame-system structure something like the following, where S\], $2, and S3are abstract slices of the flowing river shown in figure 9.</Paragraph> <Paragraph position="17"> There are many more nuances to fill in. What is &quot;stirring up&quot; and why would it keep the wolf from drinking? One might normally assign default floating objects to the S's, but here $3 interacts with &quot;stirring up&quot; to yield something that &quot;drink&quot; does not find acceptable. Was it &quot;deduced&quot; that stirring river-water means that $3 in the first frame should have &quot;mud&quot; assigned to it; or is this simply the default assignment for stirred water? Almost any event, action, change, flow of material, or even flow of information can be represented to a first approximation by a.two-frame generalized event. The frame-system can have slots for agents, tools, side-effects, preconditions, generalized trajectories, just as in the &quot;trans&quot; verbs of &quot;case grammar&quot; theories, but we have the additional flexibility of representing changes explicitly. To see if one. has understood an event or action, one can try to build an appropriate instantiated frame-Pair.</Paragraph> <Paragraph position="19"> However, in representing changes by simple &quot;before-after&quot; frame-pairs, we can expect to pay a price. Pointing to a pair is not the same as describing their differences. This makes it less convenient to do planning or abstract reasoning; there is no explicit place to attach information about the transformation. As a second approximation, we could label pairs of nodes that point to corresponding terminals, obtaining a structure like the &quot;comparison-notes&quot; in Winston (TR-23\]), or we might place at the top of the frame-system information describing the differences more abstractly. Something of this sort will be needed eventually.</Paragraph> <Paragraph position="20"> ~CE~510~ We condense and conventionalize, in language and thought, complex situations and sequences into compact words and symbols. Some words can perhaps be &quot;defined&quot; in elegant, simple structures, but only a small part of the meaning of &quot;trade&quot; is captured by: first frame A has x B has Y second frame B has X * A has Y Trading normally occurs in a social context of law, trust and convention. Unless we also represent these other facts, most trade transactions will be almost meaningless. It is usually essential to know that each party usually wants both things but has to compromise. It is a happy but unusual circumstance in which each trader is glad to get rid of what he has. To represent trading strategies, one could insert the basic maneuvers right into the above frame-pair scenario: in order for A to make B want X more (or want Y less) we expect him to select one of the familiar tactics: Offer more for Y.</Paragraph> <Paragraph position="21"> Explain why X is so good.</Paragraph> <Paragraph position="22"> Create favorable side-effect of B having I~sparage'the competition.</Paragraph> <Paragraph position="23"> Make B think C wants X.</Paragraph> <Paragraph position="24"> These only scratch, the surface. Trades usually occur within a * scenario tied together by more than a simple chain of events each linked to the next. No single such scenario will do; when a clue about trading appears it is essential to guess which of the different available scenarios is most tikely to be useful.</Paragraph> <Paragraph position="25"> Charniak's thesis (TR-266) studies questions about transactions that seem easy for people to comprehend yet obviously need rich default structures. We find in elementary school reading books such stories aS: Jane was invited to Jack's Birthday Party.</Paragraph> <Paragraph position="26"> She wonderedif he would like a kite.</Paragraph> <Paragraph position="27"> She went to her room and shook her piggy bank.</Paragraph> <Paragraph position="28"> It made no sound.</Paragraph> <Paragraph position="29"> We first hear that Jane is invited to Jack's Birthday Party. Without the party scenario, or at least an invitation scenario, the second line seems rather mysterious: She wondered if he would like a kite.</Paragraph> <Paragraph position="30"> To explain one's rapid comprehension ofthis, we make a somewhat radical proposal: to represent explicitly, in the frame for a scenario structure, pointers to a collection of the most serious problems and questions commonly associated with it.</Paragraph> <Paragraph position="31"> In fact we shall consider the idea that the frame terminals are exactly those questions.</Paragraph> <Paragraph position="32"> Thus, for the birthday party: Y must get P for X ........ Choose P! X must like P ........ - .... Will X likeP? Buy P -:- ............ --- Where to buy P? Get money to buy P .... Where to get money? (Sub-questions of the &quot;present&quot; frame?) Y must dress up What should Y wear? Certainly these are one's first concerns when one is invited to a partY.Th e 'reader is free to wonder * whether this solution is acceptable. The question &quot;Will X like P?&quot; certainly matches &quot;She wondered if he would like a kite?&quot; and correctly assigns the kite to P. But is:our world regular enough that such question sets could be pro-compiled to make this mechanism often work smoothly? The answer is mixed. We do indeed * expect many such questions; we surely do not expect all o! them. But surely &quot;expertise&quot; consists partly in not having to realize, a._bb i nitio, what are the outstanding problems and interactions insituations. Notice, for example, that there is no default assignment for the Present in our party-scenario fr-ame. This mandates attention to that assignment problem and prepares us for a Possible thematic concern. In any case, we probably need a more active mechanism for understanding &quot;wondered&quot; which can apply the information currently in the frame to produce an expectation of what Jane will think about.</Paragraph> <Paragraph position="33"> The key words and ideas of a discourse evoke substantial thematic or scenario structures, drawn from memory with rich default assumptions. In any event, the individual statements of a * discourse lead to temporary representations -- which seem to correspond to what contemporary linguists call &quot;deep structures&quot; -- which are then quickly rearranged or consumed in elaborating the growing scenario representation. In order of &quot;scale,&quot; among the ingredients of such a structure there might be these kinds of levels: EXCU~E~ We can think of a frame as describing an &quot;ideal.&quot; If an ideal does not match reality because it is &quot;basically&quot; wrong, it must be replaced.</Paragraph> <Paragraph position="34"> But it is in the nature of'ideals.that they are really elegant simplifications; their attractiveness derives from their simplicity, but their real power depends upon additional knowledge about interactions between them! Accordingly we need not abandon an ideal because of a failure to instantiate it, provided one can explain the discrepancy in terms of such an interaction. Here are some examples in which such an &quot;excuse&quot; can save a failing match: OCCLUSION: A table, in a certain view, should have four legs, but a chair might occlude one of them One can look for things like T-joints and shadows to support such an excuse.</Paragraph> <Paragraph position="35"> FUNCTIONAL VARIANT: A chair-leg is usually a stick, geometrically; but more important, it is functionally a support. Therefore, a strong center post, with an adequate base plate, should be an acceptable replacement for all the legs. Many objects are multiple purpose and need functional rather than physical descriptions.</Paragraph> <Paragraph position="36"> BROKEN: A visually missing component could be explained as in fact physically missing, or it could be broken.</Paragraph> <Paragraph position="37"> Reality has a variety of ways to frustrate ideals.</Paragraph> <Paragraph position="38"> PARASITIC CONTEXTS: An object that is just like a chair, except in size, could be (and probably is) a toy chair. The complaint &quot;too small&quot; could often be so interpreted in contexts with other things too small, children playing, peculiarly large &quot;grain,&quot; and so forth.</Paragraph> <Paragraph position="39"> In most of those examples, the kinds of knowledge to make the repair -- and thus salvage the current frame -- are &quot;general&quot; enough usually to be attached to the thematic context of a superior frame.</Paragraph> <Paragraph position="40"> In moving about a familiar house, we already know a dependable structure for &quot;information retrieval&quot; of room frames. When we move through Door D, in Room X, we expect to enter Room Y (assuming D I.s not the Exit). We could represent this as an action transformation of the simplest kind, consisting of pointers between pairs of room frames of a particular house system.</Paragraph> <Paragraph position="41"> When the house is not familiar, a &quot;!ogical&quot; strategy might be to move up a level of classification: when you leave one room, you may not know which room you are entering, but you usually know that it is some room. Thus, one can partially evade lack of specific information by dealing with classes -- and one has to use some form of abstraction or generalization to escape the dilemma of Bartlett's commander.</Paragraph> <Paragraph position="42"> It?...</Paragraph> <Paragraph position="43"> Winston's thesis (TR-23\]) proposes a way to construct a retrieval system that cart represent classes but has additional flexibility. His retrieval pointers can be made to represent goal requirements and action effects as well as class memberships.</Paragraph> <Paragraph position="44"> What does it mean to expect a chair? Typically, four legs, some assortment of rungs, a level seat, an upper back. One expects also certain relations between these &quot;parts.&quot; The legs must be below the seat, the back above. The legs must be supported by the floo'r. The seat must be horizontal, the back vertical, and so forth.</Paragraph> <Paragraph position="45"> Now suppose that this description does not match; the vision system finds four legs, a level plane, but no back. The &quot;difference&quot; between what we expect and what we see is &quot;too few backs.&quot; This suggests not a chair, but a table or a bench.</Paragraph> <Paragraph position="46"> Winston proposes pointers from each description in memory to other descriptions, with each pointer labelled by a difference marker. Complaints about mismatch are matched to the difference pointers leaving the frame and thus may propose a better candidate frame. Winston calls the resulting structure a Similarity Network.</Paragraph> <Section position="1" start_page="0" end_page="0" type="sub_section"> <SectionTitle> Is a Similarity Network practical? At first sight, </SectionTitle> <Paragraph position="0"> there might seem to be a danger of unconstrained growth of memory. If there are N frames, and K kinds of differences, then there could be as many as K*N*N interframe pointers.</Paragraph> <Paragraph position="1"> One might fear that: (\]) If N is large, say 10, then N*N is very large -of the order of 10 -- which might be impractical, at least for human memory.</Paragraph> <Paragraph position="2"> (2) There might be so many pointers for a given difference and a given frame that the system will not be selective enough to be useful.</Paragraph> <Paragraph position="3"> (3) K itself might be very large if the system is sensitive to many different kinds of issues. But, according to contemporary opinions (admittedly, not very conclusive) about the rate of storage into human long-term memory there are probably not enough seconds in a lifetime to cause a saturation problem.</Paragraph> <Paragraph position="4"> So the real problem, paradoxically, is that there will be too few connections! One cannot expect to have enough time to fill out the network to saturation Given two frames that should be linked by a difference, we cannot count on that pointer being there; the problem may not have occurred before. However, in the next section we see how to partially escape this p~oblem.</Paragraph> <Paragraph position="6"/> </Section> <Section position="2" start_page="0" end_page="0" type="sub_section"> <SectionTitle> Qualifiers and relations concerning </SectionTitle> <Paragraph position="0"> participants, instruments, trajectories and strategies, goals, consequences and sideeffects. null Thematic Frames --- Scenarios concerned with topics, activities, portraits, setting.</Paragraph> <Paragraph position="1"> Outstanding *problems and strategies commonly connected with topics.</Paragraph> <Paragraph position="2"> Narrative Frames --- Skeleton forms for typical stories, explanations, and arguments.</Paragraph> <Paragraph position="3"> Conventions about loci, protagonists, plot forms, development, etc., designed to help a listener construct.a new, inatantieted Thematic Frame in his own mind.</Paragraph> </Section> </Section> class="xml-element"></Paper>